Short-term forecasting optimization algorithm for unsteady wind speed signal based on wavelet analysis method and neutral networks method

Hui Liu, Hong Qi Tian, Chao Chen, Yan Fei Li

Research output: Contribution to journalArticleResearchpeer-review

Abstract

To promote the forecasting performance of traditional neural networks for non-stationary wind speed signal, an optimization algorithm was proposed based on wavelet analysis method and neural networks method. This optimization algorithm employed wavelet analysis method to make signal decomposition and reconstruction calculations for original wind speed series attain more steady sub-series. Then BP neural networks method was used to build unsteady prediction models for each layer to realize multi-step rolling forecast calculation. Simulation results show that the optimization algorithm can attain high-precision multi-step ahead forecast results, respectively improve forecast precision of traditional BP neural networks method by 55.56%, 32.43% and 34.58%, and the mean relative error of one-step, three-step and five-step ahead forecast are 0.48%, 1.50% and 2.97%. The optimization has signal decomposition and self-learning ability.

Original languageEnglish
Pages (from-to)2704-2711
Number of pages8
JournalZhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology)
Volume42
Issue number9
Publication statusPublished - Sep 2011

Keywords

  • Neural networks method
  • Optimization algorithm
  • Wavelet analysis method
  • Wind speed forecast

Cite this

@article{74792ae6c2b746228393caa0e9edf5e3,
title = "Short-term forecasting optimization algorithm for unsteady wind speed signal based on wavelet analysis method and neutral networks method",
abstract = "To promote the forecasting performance of traditional neural networks for non-stationary wind speed signal, an optimization algorithm was proposed based on wavelet analysis method and neural networks method. This optimization algorithm employed wavelet analysis method to make signal decomposition and reconstruction calculations for original wind speed series attain more steady sub-series. Then BP neural networks method was used to build unsteady prediction models for each layer to realize multi-step rolling forecast calculation. Simulation results show that the optimization algorithm can attain high-precision multi-step ahead forecast results, respectively improve forecast precision of traditional BP neural networks method by 55.56{\%}, 32.43{\%} and 34.58{\%}, and the mean relative error of one-step, three-step and five-step ahead forecast are 0.48{\%}, 1.50{\%} and 2.97{\%}. The optimization has signal decomposition and self-learning ability.",
keywords = "Neural networks method, Optimization algorithm, Wavelet analysis method, Wind speed forecast",
author = "Hui Liu and Tian, {Hong Qi} and Chao Chen and Li, {Yan Fei}",
year = "2011",
month = "9",
language = "English",
volume = "42",
pages = "2704--2711",
journal = "Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology)",
issn = "1672-7207",
number = "9",

}

TY - JOUR

T1 - Short-term forecasting optimization algorithm for unsteady wind speed signal based on wavelet analysis method and neutral networks method

AU - Liu, Hui

AU - Tian, Hong Qi

AU - Chen, Chao

AU - Li, Yan Fei

PY - 2011/9

Y1 - 2011/9

N2 - To promote the forecasting performance of traditional neural networks for non-stationary wind speed signal, an optimization algorithm was proposed based on wavelet analysis method and neural networks method. This optimization algorithm employed wavelet analysis method to make signal decomposition and reconstruction calculations for original wind speed series attain more steady sub-series. Then BP neural networks method was used to build unsteady prediction models for each layer to realize multi-step rolling forecast calculation. Simulation results show that the optimization algorithm can attain high-precision multi-step ahead forecast results, respectively improve forecast precision of traditional BP neural networks method by 55.56%, 32.43% and 34.58%, and the mean relative error of one-step, three-step and five-step ahead forecast are 0.48%, 1.50% and 2.97%. The optimization has signal decomposition and self-learning ability.

AB - To promote the forecasting performance of traditional neural networks for non-stationary wind speed signal, an optimization algorithm was proposed based on wavelet analysis method and neural networks method. This optimization algorithm employed wavelet analysis method to make signal decomposition and reconstruction calculations for original wind speed series attain more steady sub-series. Then BP neural networks method was used to build unsteady prediction models for each layer to realize multi-step rolling forecast calculation. Simulation results show that the optimization algorithm can attain high-precision multi-step ahead forecast results, respectively improve forecast precision of traditional BP neural networks method by 55.56%, 32.43% and 34.58%, and the mean relative error of one-step, three-step and five-step ahead forecast are 0.48%, 1.50% and 2.97%. The optimization has signal decomposition and self-learning ability.

KW - Neural networks method

KW - Optimization algorithm

KW - Wavelet analysis method

KW - Wind speed forecast

UR - http://www.scopus.com/inward/record.url?scp=80355125428&partnerID=8YFLogxK

M3 - Article

VL - 42

SP - 2704

EP - 2711

JO - Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology)

JF - Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology)

SN - 1672-7207

IS - 9

ER -